Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 2210
    Prev
    Next
    INDEX
    Explanations

    ня

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    杀了
    -0.09
    مرض
    -0.09
    喝了
    -0.09
    写了
    -0.09
     Qaeda
    -0.09
    ']."</
    -0.08
    找了
    -0.08
    想了
    -0.08
     verschied
    -0.08
    吸引了
    -0.08
    POSITIVE LOGITS
    但是他
    0.13
    也希望
    0.11
    所以他
    0.11
    所以我
    0.10
    也是很
    0.10
    覺得
    0.10
    绝对是
    0.10
    ができ
    0.09
    不错的
    0.09
    被誉
    0.08
    Activations Density 1.527%

    No Known Activations